R 中的降维
Matt Pickard
Owner, Pickard Predictives, LLC
df %>% ncol()
3
删除或合并几乎不带新信息的特征
df %>% summarize( across( everything(), ~ var(., na.rm = TRUE))) %>% pivot_longer( everything(), "feature", "variance")
df %>% summarize( across( everything(), ~ var(., na.rm = TRUE))) %>%
pivot_longer( everything(), "feature", "variance")
# A tibble: 7 × 2 feature variance <chr> <dbl> 1 sqft_living 843534. 2 sqft_above 685735. 3 sqft_basement 195873. 4 sqft_living_near15 475480. 5 sqft_lot_near15 863386815. 6 num_garages 0 7 num_hvac_units 0
library(corrr) house_sales_df %>% select(where(is.numeric)) %>% correlate() %>% shave() %>% rplot(print_cor = TRUE) + theme(axis.text.x = element_text(angle = 90, hjust = 1))
library(corrr)
house_sales_df %>% select(where(is.numeric)) %>%
correlate() %>%
shave() %>%
rplot(print_cor = TRUE) +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
Preparing Video For Download...
